Siliverstovs, Boriss Kholodilin, Konstantin Arkadievich
DIW Discussion Papers 598
This paper suggests a novel approach to pre-selection of the component series of the diffusion index based on their individual forecasting performance. It is shown that this targeted selection allows substantially improving the forecasting ability compared to the diffusion index models that are based on the largest available data set.
Diffusion index ; forecasting ; optimal subset of data